How to Use the Airship MCP in LangChain

Q: Can LangChain see my Airship push history?

Yes, by calling getpushstatus inside your agent, you retrieve real-time delivery logs. You can then use that data to decide if a follow-up message is necessary.

Build complex push notification chains in LangChain by linking Airship tool calls directly into your ReAct agent logic.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Airship MCP to LangChain

Create your Vinkius account to connect Airship to LangChain and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Airship with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Airship actions in LangChain

Feed the output of `list_segments` directly into a `send_push_notification` call within your agent's reasoning loop. You define the logic flow, and the agent executes the sequence without manual intervention. Tracing every step in LangSmith gives you a clear view of how your chain handles audience data. You'll see exactly which tool inputs triggered a specific notification delivery.

Manage audience data with LangChain

Query your static lists and tags using `list_static_lists` and `list_tags` to inform agent decisions. Your pipeline pulls fresh audience metadata before triggering any outbound communication. This keeps your messaging logic grounded in real-time account state. If a user isn't in the right segment, the chain stops before it makes a mistake.

Automate user device mapping for LangChain

Call `associate_named_user` to bridge the gap between your internal databases and mobile device IDs. Your agent handles the heavy lifting of mapping cross-platform identifiers. Checking status with `get_push_status` ensures that your agent knows if a message reached the intended device. It’s a closed-loop system for tracking engagement.

Setup guide

Set up Airship MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Airship tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "airship-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Airship transactions"
    })
    print(result["messages"][-1].content)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Airship. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Airship now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Airship MCP in LangChain

You use the MultiServerMCPClient to point your LangChain environment at the Vinkius endpoint. Once linked, the agent pulls the tool definitions automatically and starts building chains.

Yes, by calling `get_push_status` inside your agent, you retrieve real-time delivery logs. You can then use that data to decide if a follow-up message is necessary.

Vinkius isolates your session, ensuring that only your authorized agent interacts with your account. Your credentials stay behind the endpoint, away from any public exposure.

The agent receives an error message directly from the tool. You can configure your chain to catch these exceptions and retry the action or log the failure.

The server only returns device metadata and user tags that you explicitly request. We treat these identifiers as private, and the MCP protocol ensures they transit through a secure memory-mapped sandbox.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript